DeepSeek V4 Flash 0731
deepseek/deepseek-v4-flash-0731
Compare with DeepSeek V4 Flash 0423, DeepSeek V4 Pro 0423, DeepSeek V4 Pro 0813
CompareDeepSeek V4 Flash 0731
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
Alibabaalibaba | Healthy | 100% | 99.12% | 98.68% | 98.68% | 2.11s | 14.4s | 55 tps | 1.0M | $0.402 / $1.21 |
| Healthy | 100% | 99.47% | 99.51% | 99.51% | 1.42s | 12.4s | 85 tps | 1.0M | $0.440 / $1.32 | |
| Healthy | 100% | 95.48% | 97.74% | 97.74% | 443ms | 4.37s | 67 tps | 1.0M | $0.130 / $0.260 | |
Cloudflarecloudflare | Down | 100% | 96.74% | 98.00% | 98.00% | 636ms | 8.05s | 82 tps | 1.3M | $0.440 / $1.32 |
DeepSeekdeepseek | Healthy | 100% | 99.03% | 83.38% | 83.38% | 750ms | 3.28s | 77 tps | 1.0M | $0.440 / $1.32 |
| Healthy | 99.98% | 99.64% | 99.80% | 99.80% | 570ms | 7.87s | 117 tps | 262K | $0.130 / $0.280 | |
| Healthy | 99.97% | 99.43% | 99.35% | 99.35% | 1.28s | 9.88s | 92 tps | 1.0M | $0.140 / $0.280 | |
| Healthy | 99.90% | 99.18% | 97.33% | 97.33% | 644ms | 6.79s | 17 tps | 1.0M | $0.080 / $0.180 | |
Waferwafer/fast | Healthy | 99.88% | 98.38% | 98.62% | 98.62% | 877ms | 11.3s | 185 tps | 1.0M | $0.280 / $0.560 |
| Degraded | 99.85% | 88.92% | 79.13% | 79.13% | 885ms | 26.0s | 38 tps | 262K | $0.077 / $0.155 | |
| Healthy | 99.80% | 99.59% | 99.64% | 99.64% | 881ms | 6.22s | 64 tps | 1.0M | $0.070 / $0.140 | |
| Healthy | 99.79% | 99.75% | 99.15% | 99.15% | 666ms | 11.6s | 53 tps | 1.0M | $0.130 / $0.280 | |
| Healthy | 99.79% | 99.24% | 99.45% | 99.45% | 877ms | 6.15s | 89 tps | 1.0M | $0.140 / $0.280 | |
| Healthy | 99.70% | 98.56% | 98.73% | 98.73% | 2.05s | 12.8s | 51 tps | 1.0M | $0.140 / $0.280 | |
DigitalOceandigitalocean | Healthy | 99.67% | 97.34% | 95.79% | 95.79% | 794ms | 5.66s | 10 tps | 1.0M | $0.080 / $0.252 |
| Healthy | 99.66% | 98.87% | 99.18% | 99.18% | 2.25s | 11.6s | 62 tps | 1.0M | $0.084 / $0.168 | |
| Healthy | 99.59% | 99.53% | 98.59% | 98.59% | 1.47s | 10.3s | 10 tps | 1.0M | $0.120 / $0.278 | |
Togethertogether | Degraded | 99.49% | 97.33% | 97.24% | 97.24% | 827ms | 9.01s | 53 tps | 1.0M | $0.140 / $0.280 |
| Healthy | 99.22% | 98.14% | 98.18% | 98.18% | 745ms | 10.8s | 54 tps | 1.0M | $0.140 / $0.280 | |
| Healthy | 99.17% | 95.26% | 95.39% | 95.39% | 908ms | 9.19s | 50 tps | 1.0M | $0.145 / $0.450 | |
| Healthy | 99.10% | 98.87% | 98.54% | 98.54% | 711ms | 13.9s | 43 tps | 1.0M | $0.080 / $0.180 | |
| Healthy | 99.06% | 99.49% | 98.98% | 98.98% | 983ms | 6.29s | 163 tps | 262K | $0.220 / $0.660 | |
Venicevenice | Healthy | 99.02% | 97.26% | 97.45% | 97.45% | 794ms | 12.2s | 75 tps | 1.0M | $0.175 / $0.350 |
Phalaphala | Healthy | 98.84% | 98.40% | 97.80% | 97.80% | 744ms | 7.91s | 36 tps | 1.0M | $0.200 / $0.400 |
| Healthy | 98.70% | 97.73% | 98.58% | 98.58% | 3.08s | 50.9s | 15 tps | 1.0M | $0.065 / $0.180 | |
Fireworksfireworks | Healthy | 98.52% | 98.80% | 97.41% | 97.41% | 865ms | 16.0s | 52 tps | 1.0M | $0.140 / $0.280 |
| Healthy | 98.48% | 98.90% | 97.28% | 97.28% | 1.64s | 29.7s | 43 tps | 1.0M | $0.079 / $0.157 | |
| Healthy | 97.15% | 96.95% | 97.73% | 97.73% | 808ms | 11.2s | 67 tps | 262K | $0.189 / $0.420 | |
| Degraded | 96.61% | 98.21% | 97.93% | 97.93% | 1.88s | 13.7s | 28 tps | 131K | $0.140 / $0.280 | |
| Healthy | 96.47% | 94.18% | 94.87% | 94.87% | 2.81s | 23.6s | 11 tps | 262K | $0.065 / $0.180 |
- Alibaba100%Healthy24h 99.12%
- 7d
- 98.68%
- 30d
- 98.68%
- p50
- 2.11s
- p99
- 14.4s
- Throughput
- 55 tps
- Context
- 1.0M
- $/Mtok
- $0.402 / $1.21
alibaba - AtlasCloud100%Healthy24h 99.47%
- 7d
- 99.51%
- 30d
- 99.51%
- p50
- 1.42s
- p99
- 12.4s
- Throughput
- 85 tps
- Context
- 1.0M
- $/Mtok
- $0.440 / $1.32
atlas-cloud/fp4fp4 - BaseTen100%Healthy24h 95.48%
- 7d
- 97.74%
- 30d
- 97.74%
- p50
- 443ms
- p99
- 4.37s
- Throughput
- 67 tps
- Context
- 1.0M
- $/Mtok
- $0.130 / $0.260
baseten/fp8fp8 - Cloudflare100%Down24h 96.74%
- 7d
- 98.00%
- 30d
- 98.00%
- p50
- 636ms
- p99
- 8.05s
- Throughput
- 82 tps
- Context
- 1.3M
- $/Mtok
- $0.440 / $1.32
cloudflare - DeepSeek100%Healthy24h 99.03%
- 7d
- 83.38%
- 30d
- 83.38%
- p50
- 750ms
- p99
- 3.28s
- Throughput
- 77 tps
- Context
- 1.0M
- $/Mtok
- $0.440 / $1.32
deepseek - CoreWeave99.98%Healthy24h 99.64%
- 7d
- 99.80%
- 30d
- 99.80%
- p50
- 570ms
- p99
- 7.87s
- Throughput
- 117 tps
- Context
- 262K
- $/Mtok
- $0.130 / $0.280
coreweave/fp8fp8 - Novita99.97%Healthy24h 99.43%
- 7d
- 99.35%
- 30d
- 99.35%
- p50
- 1.28s
- p99
- 9.88s
- Throughput
- 92 tps
- Context
- 1.0M
- $/Mtok
- $0.140 / $0.280
novita/fp8fp8 - Ambient99.90%Healthy24h 99.18%
- 7d
- 97.33%
- 30d
- 97.33%
- p50
- 644ms
- p99
- 6.79s
- Throughput
- 17 tps
- Context
- 1.0M
- $/Mtok
- $0.080 / $0.180
ambient/fp4fp4 - Wafer99.88%Healthy24h 98.38%
- 7d
- 98.62%
- 30d
- 98.62%
- p50
- 877ms
- p99
- 11.3s
- Throughput
- 185 tps
- Context
- 1.0M
- $/Mtok
- $0.280 / $0.560
wafer/fast - Decart99.85%Degraded24h 88.92%
- 7d
- 79.13%
- 30d
- 79.13%
- p50
- 885ms
- p99
- 26.0s
- Throughput
- 38 tps
- Context
- 262K
- $/Mtok
- $0.077 / $0.155
decart/fp4fp4 - Relace99.80%Healthy24h 99.59%
- 7d
- 99.64%
- 30d
- 99.64%
- p50
- 881ms
- p99
- 6.22s
- Throughput
- 64 tps
- Context
- 1.0M
- $/Mtok
- $0.070 / $0.140
relace/fp4fp4 - Inceptron99.79%Healthy24h 99.75%
- 7d
- 99.15%
- 30d
- 99.15%
- p50
- 666ms
- p99
- 11.6s
- Throughput
- 53 tps
- Context
- 1.0M
- $/Mtok
- $0.130 / $0.280
inceptron/fp4fp4 - Baidu99.79%Healthy24h 99.24%
- 7d
- 99.45%
- 30d
- 99.45%
- p50
- 877ms
- p99
- 6.15s
- Throughput
- 89 tps
- Context
- 1.0M
- $/Mtok
- $0.140 / $0.280
baidu/fp8fp8 - SiliconFlow99.70%Healthy24h 98.56%
- 7d
- 98.73%
- 30d
- 98.73%
- p50
- 2.05s
- p99
- 12.8s
- Throughput
- 51 tps
- Context
- 1.0M
- $/Mtok
- $0.140 / $0.280
siliconflow/fp8fp8 - DigitalOcean99.67%Healthy24h 97.34%
- 7d
- 95.79%
- 30d
- 95.79%
- p50
- 794ms
- p99
- 5.66s
- Throughput
- 10 tps
- Context
- 1.0M
- $/Mtok
- $0.080 / $0.252
digitalocean - GMICloud99.66%Healthy24h 98.87%
- 7d
- 99.18%
- 30d
- 99.18%
- p50
- 2.25s
- p99
- 11.6s
- Throughput
- 62 tps
- Context
- 1.0M
- $/Mtok
- $0.084 / $0.168
gmicloud/fp8fp8 - Morph99.59%Healthy24h 99.53%
- 7d
- 98.59%
- 30d
- 98.59%
- p50
- 1.47s
- p99
- 10.3s
- Throughput
- 10 tps
- Context
- 1.0M
- $/Mtok
- $0.120 / $0.278
morph/bf16bf16 - Together99.49%Degraded24h 97.33%
- 7d
- 97.24%
- 30d
- 97.24%
- p50
- 827ms
- p99
- 9.01s
- Throughput
- 53 tps
- Context
- 1.0M
- $/Mtok
- $0.140 / $0.280
together - Parasail99.22%Healthy24h 98.14%
- 7d
- 98.18%
- 30d
- 98.18%
- p50
- 745ms
- p99
- 10.8s
- Throughput
- 54 tps
- Context
- 1.0M
- $/Mtok
- $0.140 / $0.280
parasail/fp8fp8 - Mancer 299.17%Healthy24h 95.26%
- 7d
- 95.39%
- 30d
- 95.39%
- p50
- 908ms
- p99
- 9.19s
- Throughput
- 50 tps
- Context
- 1.0M
- $/Mtok
- $0.145 / $0.450
mancer/fp8fp8 - DeepInfra99.10%Healthy24h 98.87%
- 7d
- 98.54%
- 30d
- 98.54%
- p50
- 711ms
- p99
- 13.9s
- Throughput
- 43 tps
- Context
- 1.0M
- $/Mtok
- $0.080 / $0.180
deepinfra/fp8fp8 - Reka99.06%Healthy24h 99.49%
- 7d
- 98.98%
- 30d
- 98.98%
- p50
- 983ms
- p99
- 6.29s
- Throughput
- 163 tps
- Context
- 262K
- $/Mtok
- $0.220 / $0.660
reka/fp4fp4 - Venice99.02%Healthy24h 97.26%
- 7d
- 97.45%
- 30d
- 97.45%
- p50
- 794ms
- p99
- 12.2s
- Throughput
- 75 tps
- Context
- 1.0M
- $/Mtok
- $0.175 / $0.350
venice - Phala98.84%Healthy24h 98.40%
- 7d
- 97.80%
- 30d
- 97.80%
- p50
- 744ms
- p99
- 7.91s
- Throughput
- 36 tps
- Context
- 1.0M
- $/Mtok
- $0.200 / $0.400
phala - Sail Research98.70%Healthy24h 97.73%
- 7d
- 98.58%
- 30d
- 98.58%
- p50
- 3.08s
- p99
- 50.9s
- Throughput
- 15 tps
- Context
- 1.0M
- $/Mtok
- $0.065 / $0.180
sail-research/fp4fp4 - Fireworks98.52%Healthy24h 98.80%
- 7d
- 97.41%
- 30d
- 97.41%
- p50
- 865ms
- p99
- 16.0s
- Throughput
- 52 tps
- Context
- 1.0M
- $/Mtok
- $0.140 / $0.280
fireworks - StreamLake98.48%Healthy24h 98.90%
- 7d
- 97.28%
- 30d
- 97.28%
- p50
- 1.64s
- p99
- 29.7s
- Throughput
- 43 tps
- Context
- 1.0M
- $/Mtok
- $0.079 / $0.157
streamlake/fp8fp8 - Io Net97.15%Healthy24h 96.95%
- 7d
- 97.73%
- 30d
- 97.73%
- p50
- 808ms
- p99
- 11.2s
- Throughput
- 67 tps
- Context
- 262K
- $/Mtok
- $0.189 / $0.420
io-net/fp8fp8 - AkashML96.61%Degraded24h 98.21%
- 7d
- 97.93%
- 30d
- 97.93%
- p50
- 1.88s
- p99
- 13.7s
- Throughput
- 28 tps
- Context
- 131K
- $/Mtok
- $0.140 / $0.280
akashml/fp8fp8 - OpenInference96.47%Healthy24h 94.18%
- 7d
- 94.87%
- 30d
- 94.87%
- p50
- 2.81s
- p99
- 23.6s
- Throughput
- 11 tps
- Context
- 262K
- $/Mtok
- $0.065 / $0.180
open-inference/fp4fp4
Measured 5m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
Price changes
- DeepSeek V4 Flash 0731OpenInferenceopen-inference/fp4$0.060 / $0.180 → $0.065 / $0.1802026-08-21 08:05 UTC
- DeepSeek V4 Flash 0731Morphmorph/bf16$0.120 / $0.278 → $0.120 / $0.2782026-08-21 08:05 UTC
- DeepSeek V4 Flash 0731OpenInferenceopen-inference/fp4$0.080 / $0.180 → $0.060 / $0.1802026-08-21 07:55 UTC
- DeepSeek V4 Flash 0731OpenInferenceopen-inference/fp4$0.065 / $0.140 → $0.080 / $0.1802026-08-21 06:25 UTC
- DeepSeek V4 Flash 0731DeepSeekdeepseek$0.220 / $0.660 → $0.440 / $1.322026-08-21 06:06 UTC
- DeepSeek V4 Flash 0731Fireworksfireworks$0.220 / $0.660 → $0.140 / $0.2802026-08-21 05:25 UTC
- DeepSeek V4 Flash 0731Fireworksfireworks$0.140 / $0.280 → $0.220 / $0.6602026-08-21 04:50 UTC
- DeepSeek V4 Flash 0731DeepSeekdeepseek$0.440 / $1.32 → $0.220 / $0.6602026-08-21 04:10 UTC
- DeepSeek V4 Flash 0731DeepSeekdeepseek$0.220 / $0.660 → $0.440 / $1.322026-08-21 01:10 UTC
- DeepSeek V4 Flash 0731Decartdecart/fp4$0.066 / $0.131 → $0.077 / $0.1552026-08-21 00:50 UTC
- DeepSeek V4 Flash 0731Morphmorph/bf16$0.139 / $0.278 → $0.120 / $0.2782026-08-21 00:45 UTC
- DeepSeek V4 Flash 0731AtlasCloudatlas-cloud/fp4$0.140 / $0.280 → $0.440 / $1.322026-08-21 00:10 UTC
- DeepSeek V4 Flash 0731Alibabaalibaba$0.201 / $0.603 → $0.402 / $1.212026-08-21 00:05 UTC
- DeepSeek V4 Flash 0731StreamLakestreamlake/fp8$0.067 / $0.134 → $0.079 / $0.1572026-08-20 23:50 UTC
- DeepSeek V4 Flash 0731Baidubaidu/fp8$0.069 / $0.137 → $0.140 / $0.2802026-08-20 23:40 UTC
- DeepSeek V4 Flash 0731Decartdecart/fp4$0.076 / $0.153 → $0.066 / $0.1312026-08-20 19:55 UTC
- DeepSeek V4 Flash 0731Ambientambient/fp4$0.800 / $0.180 → $0.080 / $0.1802026-08-20 19:30 UTC
- DeepSeek V4 Flash 0731StreamLakestreamlake/fp8$0.078 / $0.157 → $0.067 / $0.1342026-08-20 19:05 UTC
- DeepSeek V4 Flash 0731Ambientambient/fp4$0.140 / $0.280 → $0.800 / $0.1802026-08-20 18:50 UTC
- DeepSeek V4 Flash 0731GMICloudgmicloud/fp8$0.112 / $0.224 → $0.084 / $0.1682026-08-20 18:45 UTC
- DeepSeek V4 Flash 0731Baidubaidu/fp8$0.080 / $0.160 → $0.069 / $0.1372026-08-20 18:45 UTC
- DeepSeek V4 Flash 0731Alibabaalibaba$0.242 / $0.726 → $0.201 / $0.6032026-08-20 16:35 UTC
- DeepSeek V4 Flash 0731Alibabaalibaba$0.484 / $1.45 → $0.242 / $0.7262026-08-20 14:10 UTC
- DeepSeek V4 Flash 0731StreamLakestreamlake/fp8$0.079 / $0.157 → $0.078 / $0.1572026-08-20 13:05 UTC
- DeepSeek V4 Flash 0731Baidubaidu/fp8$0.140 / $0.280 → $0.080 / $0.1602026-08-20 12:50 UTC
- DeepSeek V4 Flash 0731DeepSeekdeepseek$0.440 / $1.32 → $0.220 / $0.6602026-08-20 10:10 UTC
- DeepSeek V4 Flash 0731Io Netio-net/fp8$0.149 / $0.320 → $0.189 / $0.4202026-08-20 09:25 UTC
- DeepSeek V4 Flash 0731Rekareka/fp4$0.220 / $0.660 → $0.220 / $0.6602026-08-20 08:05 UTC
- DeepSeek V4 Flash 0731DeepSeekdeepseek$0.220 / $0.660 → $0.440 / $1.322026-08-20 06:10 UTC
- DeepSeek V4 Flash 0731Cloudflarecloudflare$0.080 / $0.180 → $0.440 / $1.322026-08-20 05:50 UTC
History
Availability
Axis starts at 90% so small differences stay visible; it expands to 0 when an endpoint falls below.
Time to first token
Logarithmic axis — the fleet spans two orders of magnitude. P50 is OpenRouter's rolling 30-minute window.
Throughput
Median tokens per second.